; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve2p1 < %s | FileCheck %s
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve,+sme2p1 < %s | FileCheck %s
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sme2p1 -force-streaming < %s | FileCheck %s
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sme,+sve2p1 -force-streaming < %s | FileCheck %s

define <vscale x 16 x i8> @test_dupq_i8 (<vscale x 16 x i8> %zn) {
; CHECK-LABEL: test_dupq_i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    dupq z0.b, z0.b[15]
; CHECK-NEXT:    ret
  %res = call <vscale x 16 x i8> @llvm.aarch64.sve.dup.laneq.nxv16i8(<vscale x 16 x i8> %zn, i32 15)
  ret <vscale x 16 x i8> %res
}

define <vscale x 8 x i16> @test_dupq_i16 (<vscale x 8 x i16> %zn) {
; CHECK-LABEL: test_dupq_i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    dupq z0.h, z0.h[7]
; CHECK-NEXT:    ret
  %res = call <vscale x 8 x i16> @llvm.aarch64.sve.dup.laneq.nxv8i16(<vscale x 8 x i16> %zn, i32 7)
  ret <vscale x 8 x i16> %res
}

define <vscale x 4 x i32> @test_dupq__i32 (<vscale x 4 x i32> %zn) {
; CHECK-LABEL: test_dupq__i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    dupq z0.s, z0.s[3]
; CHECK-NEXT:    ret
  %res = call <vscale x 4 x i32> @llvm.aarch64.sve.dup.laneq.nxv4i32(<vscale x 4 x i32> %zn, i32 3)
  ret <vscale x 4 x i32> %res
}

define <vscale x 2 x i64> @test_dupq_i64 (<vscale x 2 x i64> %zn) {
; CHECK-LABEL: test_dupq_i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    dupq z0.d, z0.d[1]
; CHECK-NEXT:    ret
  %res = call <vscale x 2 x i64> @llvm.aarch64.sve.dup.laneq.nxv2i64(<vscale x 2 x i64> %zn, i32 1)
  ret <vscale x 2 x i64> %res
}

define <vscale x 8 x half> @test_dupq_f16(<vscale x 8 x half> %zn) {
; CHECK-LABEL: test_dupq_f16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    dupq z0.h, z0.h[4]
; CHECK-NEXT:    ret
  %res = call <vscale x 8 x half> @llvm.aarch64.sve.dup.laneq.nxv8f16(<vscale x 8 x half> %zn, i32 4)
  ret <vscale x 8 x half> %res
}

define <vscale x 4 x float> @test_dupq_f32(<vscale x 4 x float> %zn) {
; CHECK-LABEL: test_dupq_f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    dupq z0.s, z0.s[2]
; CHECK-NEXT:    ret
  %res = call <vscale x 4 x float> @llvm.aarch64.sve.dup.laneq.nxv4f32(<vscale x 4 x float> %zn, i32 2)
  ret <vscale x 4 x float> %res
}

define <vscale x 2 x double> @test_dupq_f64(<vscale x 2 x double> %zn) {
; CHECK-LABEL: test_dupq_f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    dupq z0.d, z0.d[0]
; CHECK-NEXT:    ret
  %res = call <vscale x 2 x double> @llvm.aarch64.sve.dup.laneq.nxv2f64(<vscale x 2 x double> %zn, i32 0)
  ret <vscale x 2 x double> %res
}

define <vscale x 8 x bfloat> @test_dupq_bf16(<vscale x 8 x bfloat> %zn) {
; CHECK-LABEL: test_dupq_bf16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    dupq z0.h, z0.h[1]
; CHECK-NEXT:    ret
  %res = call <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.laneq.nxv8bf16(<vscale x 8 x bfloat> %zn, i32 1)
  ret <vscale x 8 x bfloat> %res
}

declare <vscale x 16 x i8> @llvm.aarch64.sve.dup.laneq.nxv16i8(<vscale x 16 x i8>, i32)
declare <vscale x 8 x i16> @llvm.aarch64.sve.dup.laneq.nxv8i16(<vscale x 8 x i16>, i32)
declare <vscale x 4 x i32> @llvm.aarch64.sve.dup.laneq.nxv4i32(<vscale x 4 x i32>, i32)
declare <vscale x 2 x i64> @llvm.aarch64.sve.dup.laneq.nxv2i64(<vscale x 2 x i64>, i32)
declare <vscale x 8 x half> @llvm.aarch64.sve.dup.laneq.nxv8f16(<vscale x 8 x half>, i32)
declare <vscale x 4 x float> @llvm.aarch64.sve.dup.laneq.nxv4f32(<vscale x 4 x float>, i32)
declare <vscale x 2 x double> @llvm.aarch64.sve.dup.laneq.nxv2f64(<vscale x 2 x double>, i32)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.dup.laneq.nxv8bf16(<vscale x 8 x bfloat>, i32)